audit-answers

Pre-computed context

Current branch: !git branch --show-current 2>/dev/null || echo "unknown"

Variables

Arguments: $ARGUMENTS

Purpose

Independent adversarial validation of a completed /planning:interview's answers. It runs over any filled decision ledger — whether the human hand-answered the rounds or the recommendations were auto-accepted — and hands each answer to fresh-context agents that re-examine it on its merits. Only the answers they challenge or reclassify come back to the human; the rest collapse to a one-line confirmation.

The value is a producer≠critic pass over decisions the producing session is structurally the worst judge of. It is sharpest when the answers were auto-accepted — /planning:interview's accept-shorthand takes the orchestrator's own recommendations at face value, the producer grading its own work — but a hand-answered ledger benefits too: fresh validators that never saw the reasoning catch a decision made under the same session's blind spots.

This is validation, never derivation. It does NOT spawn subagents to invent answers. The interview contract already resolves every fact from the environment, so anything that reaches a round is a genuine decision — the never-auto class — and a subagent asked to derive it only reinjects the orchestrator's framing and converges to accept-all at quadratic frontier cost with a false patina of verification. Fresh-context independence is real only for checking an answer, not for producing one. So the answers are accepted first, then checked.

Preconditions

A completed /planning:interview for the topic. The skill validates whatever answers that interview persisted, in whichever form it wrote them — it does not require any single artifact: